Weld Defect Classification Using Polar Radius Signature And Neural Network
An automatic defect classification system was developed in this research using simulated image database and polar radius signature and neural network classifier to identify different types of defect in radiographic images of welds. Programs were developed by using Languange C to obtain polar r...
Saved in:
| Main Author: | |
|---|---|
| Format: | Monograph |
| Language: | en |
| Published: |
Universiti Sains Malaysia
2005
|
| Subjects: | |
| Online Access: | http://eprints.usm.my/58207/1/Weld%20Defect%20Classification%20Using%20Polar%20Radius%20Signature%20And%20Neural%20Network_Teow%20Soo%20Pei.pdf http://eprints.usm.my/58207/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1834506762292559872 |
|---|---|
| author | Teow, Soo Pei |
| author_facet | Teow, Soo Pei |
| author_sort | Teow, Soo Pei |
| building | Hamzah Sendut Library |
| collection | Institutional Repository |
| content_provider | Universiti Sains Malaysia |
| content_source | USM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | An automatic defect classification system was developed in this research using
simulated image database and polar radius signature and neural network classifier to
identify different types of defect in radiographic images of welds. Programs were
developed by using Languange C to obtain polar radius signature and roughness
parameters from simulated images for subsequent classification. The image processes
involved are blob analysis, binarization, edge detection, etc to extract polar radius signature.
Several roughness parameters such as Ra, Rq, Rz, Rp and Rv were then extracted from the
polar radius signature from the simulated images. Neural network was employed to train
the simulated data. A total of 4 defect types were studied and the classification was carried
out using several different combinations of roughness parameters and types of weld defect.
The highest accuracy of 81.25% was achieved in classifying crack and incomplete
penetration by using five parameters. Therefore, roughness parameters which are extracted
from polar radius signature have potential in weld defect classification. |
| format | Monograph |
| id | my.usm.eprints.58207 |
| institution | Universiti Sains Malaysia |
| language | en |
| publishDate | 2005 |
| publisher | Universiti Sains Malaysia |
| record_format | eprints |
| spelling | my.usm.eprints.58207 http://eprints.usm.my/58207/ Weld Defect Classification Using Polar Radius Signature And Neural Network Teow, Soo Pei T Technology TJ Mechanical engineering and machinery An automatic defect classification system was developed in this research using simulated image database and polar radius signature and neural network classifier to identify different types of defect in radiographic images of welds. Programs were developed by using Languange C to obtain polar radius signature and roughness parameters from simulated images for subsequent classification. The image processes involved are blob analysis, binarization, edge detection, etc to extract polar radius signature. Several roughness parameters such as Ra, Rq, Rz, Rp and Rv were then extracted from the polar radius signature from the simulated images. Neural network was employed to train the simulated data. A total of 4 defect types were studied and the classification was carried out using several different combinations of roughness parameters and types of weld defect. The highest accuracy of 81.25% was achieved in classifying crack and incomplete penetration by using five parameters. Therefore, roughness parameters which are extracted from polar radius signature have potential in weld defect classification. Universiti Sains Malaysia 2005-03-01 Monograph NonPeerReviewed application/pdf en http://eprints.usm.my/58207/1/Weld%20Defect%20Classification%20Using%20Polar%20Radius%20Signature%20And%20Neural%20Network_Teow%20Soo%20Pei.pdf Teow, Soo Pei (2005) Weld Defect Classification Using Polar Radius Signature And Neural Network. Project Report. Universiti Sains Malaysia, Pusat Pengajian Kejuruteraan Mekanikal. (Submitted) |
| spellingShingle | T Technology TJ Mechanical engineering and machinery Teow, Soo Pei Weld Defect Classification Using Polar Radius Signature And Neural Network |
| title | Weld Defect Classification Using Polar Radius Signature And Neural Network |
| title_full | Weld Defect Classification Using Polar Radius Signature And Neural Network |
| title_fullStr | Weld Defect Classification Using Polar Radius Signature And Neural Network |
| title_full_unstemmed | Weld Defect Classification Using Polar Radius Signature And Neural Network |
| title_short | Weld Defect Classification Using Polar Radius Signature And Neural Network |
| title_sort | weld defect classification using polar radius signature and neural network |
| topic | T Technology TJ Mechanical engineering and machinery |
| url | http://eprints.usm.my/58207/1/Weld%20Defect%20Classification%20Using%20Polar%20Radius%20Signature%20And%20Neural%20Network_Teow%20Soo%20Pei.pdf http://eprints.usm.my/58207/ |
| url_provider | http://eprints.usm.my/ |